The ConScenD Dataset: Concrete Scenarios from the highD Dataset According to ALKS Regulation UNECE R157 in OpenX

Abstract

With Regulation UNECE R157 on Automated Lane-Keeping Systems, the first framework for the introduction of passenger cars with Level 3 systems has become available in 2020. In accordance with recent research projects including academia and the automotive industry, the Regulation utilizes scenario based testing for the safety assessment. The complexity of safety validation of automated driving systems necessitates system-level simulations. The Regulation, however, is missing the required parameterization necessary for test case generation. To overcome this problem, we incorporate the exposure and consider the heterogeneous behavior of the traffic participants by extracting concrete scenarios according to Regulation's scenario definition from the established naturalistic highway dataset highD. We present a methodology to find the scenarios in real-world data, extract the parameters for modeling the scenarios and transfer them to simulation. In this process, more than 340 scenarios were extracted. OpenSCENARIO files were generated to enable an exemplary transfer of the scenarios to CARLA and esmini. We compare the trajectories to examine the similarity of the scenarios in the simulation to the recorded scenarios. In order to foster research, we publish the resulting dataset called ConScenD together with instructions for usage with both simulation tools. The dataset is available online at https://www.levelXdata.com/scenarios.

Automatic lane change scenario extraction and generation of scenarios in OpenX format from real-world data

“…In this paper, we automate this process to make the scenario generation pipeline fully automated without manually creating the OpenDRIVE file as shown in the figure 8. The whole process does not require manual intervention to create or modify any process compared to similar work in this area [4], [17].…”

“…One of the significant components of the method is the scenario extraction from video data using various computer vision techniques. In [17], authors introduce a methodology to generate concrete scenarios by extracting scenario parameters from a highD dataset for assessing the Active Lane Keeping System (ALKS). OpenSCENARIO and OpenDRIVE format describe the generated concrete scenarios and road network.…”

“…OpenSCENARIO and OpenDRIVE format describe the generated concrete scenarios and road network. [4] and [17] has proposed scenario extraction frameworks and generated scenarios represent in common format. Both approaches use mainly image-based methods, and adverse weather conditions can impact the performance of the extrac-tion method.…”

“…The proposed approach is a lidar-based method that provides more robust results in diverse environmental conditions than many image-based techniques. The framework is an automated scenario extraction pipeline that generates OpenX files from real-world data without any manual intervention required compared to similar works [4], [17]. The extraction of the scenario means we are extracting parameters from the real-world scenario.…”